Search papers, labs, and topics across Lattice.
The paper introduces Hide-and-Seek, a novel framework for detecting failures in Vision-Language-Action (VLA) models by learning to localize failure-indicative actions using only trajectory-level supervision. It achieves this by combining inter-trajectory and intra-trajectory contrastive objectives to induce temporally structured failure signals without step-level annotations. Experiments on LIBERO, VLABench, and a real-world robot show Hide-and-Seek achieves state-of-the-art multi-task failure detection performance with a practical accuracy-timeliness trade-off.
Discovering when a robot's about to fail just got easier: Hide-and-Seek pinpoints failure signals in VLA trajectories using only coarse, trajectory-level labels, ditching the need for expensive step-by-step annotations.
Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment. Detecting such failures during execution is therefore critical for the robust deployment of embodied systems. Existing failure detection methods either rely on expensive action resampling or external models, while alternatives propagate trajectory-level labels uniformly across every timestep, obscuring localized failure signals. In this paper, we propose \textbf{Hide-and-Seek}, a framework that formulates VLA failure detection as a coarsely supervised learning problem. By combining inter-trajectory and intra-trajectory contrastive objectives, Hide-and-Seek localizes failure-indicative actions and induces temporally structured failure signals from trajectory-level supervision alone, without any step-level annotation. We evaluate Hide-and-Seek on LIBERO, VLABench, and a real-world robotic platform across three representative VLA policies: OpenVLA, $\pi_0$, and $\pi_{0.5}$.Our method achieves state-of-the-art multi-task failure detection performance with a practical accuracy--timeliness trade-off under conformal prediction, and generalizes well to both seen and unseen tasks.
